How many cores does the AIBox05 CPU have?

The specification table states that the CPU is octa-core, with a maximum frequency of 2.2GHz. The GPU is Mali-G52 MC3. The NPU is 6 Tops. Standard configuration is 8GB LPDDR4 memory and 64GB storage.

What operating system does AIBox05 run?

The system is ARM Linux, and the distribution is Debian 12. Display output is 1 HDMI 2.1, supporting up to 8K. Interfaces include 4 USB 2.0, 2 USB 3.0, and 1 USB OTG.

How does AIBox05 connect to the network and to cameras?

Networking is 1 RJ45 and 1 Wi-Fi, with optional 4G all-network. It supports RTSP video stream ingest and GB28181 ingest, and different algorithm analysis tasks can be assigned per camera.

Which scenarios is AIBox05 suited for?

It integrates more than 100 AI algorithms. Application scenarios include smart communities and parks, food-service stores, and smart campuses. The device can aggregate video and run algorithm analysis at the edge.

AIBox-05 AI Video Analysis Algorithm Box

AI Box / May 2025

Model: AIBox-05

The AI edge computing server box (AIbox-05) is an intelligent application server integrating 100+ AI algorithms. With an octa-core Cortex-A55 at up to 2.2GHz, a Mali-G52 MC3, and 6T of compute, it deploys AI to the edge quickly, plug and play, for fast AI enablement.

6T compute
Octa-core 2.2GHz
Mali-G52
Edge deployment

AIBox-05 AI video analysis algorithm box

2. Product Features

Uses multiple dedicated AI algorithms.
Supports RTSP video stream ingest / GB28181 protocol ingest, and more.
Supports a two-in-one of compute and the application platform, for integrated edge deployment.
Supports remote device upgrade (when the device is online)
Open interfaces, supporting secondary development and integration
Supports custom AI algorithms.
Supports multi-channel video stream aggregation (NVR)
Different cameras can be assigned different algorithm analysis tasks

3. Specifications

Product	AI edge computing server
System parameters
System	ARM Linux (Debian 12)
CPU	Octa-core, frequency up to 2.2GHz
GPU	Mali-G52 MC3
NPU	6 Tops AI compute
Storage	Standard 8GB LPDDR4, 64GB storage
Display interface	1 HDMI 2.1, up to 8K output
Interfaces	4 USB2.0, 2 USB3.0, 1 USB OTG
	2 RS232 serial ports (RS485 optional)
Network
Network	1 RJ45, 1 WIFI, optional 4G all-network

4. Product Photos

5. AI Algorithms

Multiple AI algorithms are preloaded; algorithms can be customized for the application scenario.

Standard algorithm set	People: crowd gathering detection, illegal intrusion detection, person climbing, absence-from-post detection, monitoring-room absence detection, elevator entrapment detection, entry and exit detection, sleeping-on-duty recognition, smoking recognition, and other behavior analysis
	Vehicles: muck truck recognition, e-bike entering an elevator recognition, vehicle wrong-way recognition, non-motor vehicle illegal parking detection, vehicle illegal parking recognition, jaywalking recognition, heavy machinery recognition, pedestrian and vehicle separation recognition
	Objects: exposed earth pile detection, work uniform recognition, reflective vest recognition, face mask recognition, e-bike helmet recognition, insulating glove recognition, safety helmet recognition, fire extinguisher placement detection, protective clothing recognition, cat and dog recognition
	Environment: road litter recognition, flame recognition, flame detection, overflowing garbage recognition, corridor clutter recognition, open-door recognition for equipment rooms / power rooms / unit entrances, street-vending recognition, smoke recognition, smoke detection
Custom algorithms	Industrial inspection, production-process inspection, and quality inspection;
	Requires no fewer than 50000 samples, covering annotation, design, modeling, training, parameter tuning, compression, adaptation, and iteration

Application Functions

Data platform (cloud management platform/algorithm management platform

6. Algorithm Customization

Custom development process for deep-learning AI vision algorithms:

1. Annotate images and videos sampled on site;

Obtain the dataset, then design the model, train, and so on

After the model is generated, convert it to an RKNN model for the RKNPU chip;

7. Application Scenarios

Smart community / park

Algorithms and product applications: parking in a fire lane, area intrusion recognition, fall recognition, smoke and open flame recognition, boundary crossing detection, street vending, people counting, elevator e-bike detection, and other algorithms. Widely used for identity verification of people and vehicles at entry and exit, illegal parking, environmental sanitation checks, recognition of violations and uncivil behavior, and fire-hazard detection.

Algorithms and product applications: fire and smoke recognition, hazardous area recognition, loitering recognition, person detection, person lingering, illegal fishing / stranger intrusion, fall recognition, license plate recognition, and other algorithms. Widely used in villas, courtyards, fish ponds, farms, planting and breeding bases, and unattended stores.

Food-service stores

Algorithms and product applications: customer-flow counting, VIP customer recognition, smoking recognition, phone-call recognition, rodent recognition, chef uniform and hat detection, unattended open flame, staff procedure compliance, smoke and open flame recognition, overflowing trash bins, and other algorithms. Widely used in schools, food service, hospitals, and similar sites.

Smart campus

Student behavior analysis

Fall recognition, running recognition, climbing recognition, fighting recognition, fire and smoke detection, smoking recognition, mobile phone recognition, tripwire detection, area detection;